ARC Prize measured OpenAI's GPT-6 Astra at 62.7% on ARC-AGI-3 Semi-Private under its provider-neutral Standard harness, more than doubling the prior frontier result of 30.2% set by Claude Opus 5 in Ju…
Independent LLM-from-scratch experiments found that OpenAI's GPT-2 small (124M parameters) consistently outperformed the author's 163M-parameter models on an instruction fine-tuning task adapted from …
Fireworks post-trained Kimi K3 to create Ember-1, a model that uses roughly 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations, according to the company's announcement…
Xiaomi's MiMo-V2.6 Pro ranks No. 1 on open-weight benchmarks by weighted average despite using a classic Grouped Query Attention architecture with Sliding Window Attention at a 128-token window, accor…
Sebastian Raschka argued in a blog post that Jev, the system-one model from Typesafe.ai, should not be dismissed as "just a classifier," crediting its generalization across tasks such as classifying e…
A developer has released OpenArch, a repository of hand-written PyTorch implementations of modern open-source LLM architectures, cataloged against Sebastian Raschka's LLM Architecture Gallery. The pro…
Sebastian Raschka released a 1.5-hour "AI Reasoning Models" course on LinkedIn Learning, offered as part of LinkedIn Premium, covering how reasoning models relate to conventional LLMs and how they are…
A developer extended Sebastian Raschka's GPT-2-style code from the book "Build a Large Language Model (from Scratch)" to add mixture-of-experts support and trained a 446M-parameter model with 220M act…
OpenAI released GPT-6 Astra on September 10, 2026, pitched at workplace productivity, as an OpenAI researcher disputed The Information's characterization that the model uses "recurrent depth" or loope…
AI output is accelerating faster than human review can adapt, shifting the bottleneck from generation to verification, according to engineering teams and researchers. OpenAI claims an unreleased model…
OpenAI's Astra model is not a novel 'looped transformer' breakthrough, according to Sebastian Raschka, who explains that the technique merely reuses transformer layers and was already used in Nanbeige…
Sebastian Raschka published a video and accompanying note explaining how to set up the Python and PyTorch environment for building a reasoning model from scratch, using the `uv` package manager. The v…
Author Sebastian Raschka will host two free live Q&A sessions on September 3, 2026, about his new book Build a Reasoning Model (From Scratch), first with Sophia Yang's The AI Book Club at 10 am CT and…
The Ox Alpha LLM has been identified as GLM-5.3-Flash, a new model from Zhipu AI that introduces a hybrid attention architecture combining 34 Kimi Delta Attention layers and 11 Multi-head Latent Atten…
Anthropic announced that it will watermark text outputs from its Claude models, a technique explained in a new 48-minute video lecture by Sebastian Raschka, author of 'Build a Large Language Model Fro…
Sebastian Raschka, an AI researcher and author, published a tutorial on building an AI text detector from scratch, including dataset construction, model training, local deployment, and reinforcement l…
Sebastian Raschka's book 'Build a Reasoning Model (From Scratch)' is now available on Amazon, but readers in India are advised to order directly from Manning to avoid counterfeit black-and-white copie…
The LLMs-from-scratch repository by Sebastian Raschka surpassed 100,000 stars on GitHub, marking a milestone for the open-source project that provides from-scratch implementations of large language mo…
Sebastian Raschka's 'Build a Large Language Model (From Scratch)' and Andriy Burkov's 'The Hundred-Page Language Models Book' are among five recommended books for deepening understanding of large lang…
Moonshot AI released the full weights for Kimi K3, a 2.8-trillion-parameter open-weight model that is the largest ever released, nearly triple the size of its predecessor Kimi K2. The model validates …